- name
- image2text
- description
- Extract text from any image using tesseract OCR — works with any AI model even if it has no vision capability. Supports local file paths, web URLs (OSS/http/https), and base64 image data pasted directly from clipboard. Use when: user uploads an image and asks what's in it, screenshots or clipboard images need OCR, document images need text extraction, or any image-to-text task. Perfect for text-only AI models that can't "see" images.
image2text
Extract text from images without needing a vision-capable AI model.
Usage
python3 scripts/ocr.py <image path|URL|base64> [--lang <languages>] [--psm <mode>] [--raw]Parameters
--lang: Language codes, comma-separated, defaultchi_sim+eng
- chi_sim Simplified Chinese | chi_tra Traditional | eng English | jpn Japanese | kor Korean | and 30+ more - Combine: chi_sim+eng
--psm: Page segmentation mode, default6
- 3 Fully automatic | 6 Block-level | 4 Single line | 11 Sparse text
--raw: Output plain text only, no markers
Auto-Detects Input Type
- Local path:
/Users/xxx/Downloads/xxx.png - Web URL:
https://example.com/image.png— OSS temp links work too - Base64: Pasted image data from clipboard — just paste directly
Workflow
- Receive image input → auto-detect type (local path / URL / base64)
- URL → curl downloads to temp file
- Base64 → decode to temp file
- Run tesseract OCR
- Output plain text
Examples
OCR a Chinese receipt:
python3 scripts/ocr.py ~/Downloads/receipt.png --lang chi_simEnglish + Chinese mixed:
python3 scripts/ocr.py https://example.com/doc.jpg --lang chi_sim+engPlain text only (no markers):
python3 scripts/ocr.py /path/to/image.png --rawRequirements
- tesseract must be installed:
brew install tesseract - Language packs auto-installed with tesseract
- On Mac: binary at
/opt/homebrew/bin/tesseract - Temp files auto-deleted after execution
- For best accuracy on receipts/screenshots: try
--psm 3